SM

Biggie SmoLlm 0.15B Base

SmolLMGGUF by mradermacherUpdated 2024-08-06
Download on Hugging Face
Parameters181M
Context2K
Layers35
Architecturellama
Smallest quant0.1 GB
Quick answer

Biggie SmoLlm 0.15B Base needs about 0.9 GB of memory at Q4_K_M (a 0.1 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 15 quants, from 0.1 GB (IQ3_S) to 0.4 GB (F16).

Small 0.18B SmolLM base model for lightweight inference

Biggie SmoLlm 0.15B Base is a 0.18b parameter model built from SmolLM. It supports a 2048 token context window and is released under the MIT license. The model is available in multiple GGUF quantizations for diverse hardware.

Good at

  • Fast inference on low‑memory GPUs
  • Suitable for single‑CPU inference
  • Good baseline for further fine‑tuning

Limits

  • No vision support
  • Requires 8k context for memory estimates
  • No instruction tuning included

Best for

  • Local chatbot prototypes
  • Research prototyping
  • Edge device inference

Who it’s for. Developers and researchers needing a small, fast LLM for experimentation or deployment on limited hardware. The model is ideal for those who want to fine‑tune or merge with other checkpoints.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S0.1 GB 0.7 GB
Fits Get file →
IQ3_XS0.1 GB 0.7 GB
Fits Get file →
Q2_K0.1 GB 0.7 GB
Fits Get file →
Q3_K_S0.1 GB 0.7 GB
Fits Get file →
IQ3_M0.1 GB 0.7 GB
Fits Get file →
IQ4_XS0.1 GB 0.7 GB
Fits Get file →
Q3_K_M0.1 GB 0.7 GB
Fits Get file →
Q3_K_L0.1 GB 0.7 GB
Fits Get file →
Q4_K_S0.1 GB 0.7 GB
Fits Get file →
Q4_K_M0.1 GB 0.7 GB
Fits Get file →
Q5_K_S0.1 GB 0.7 GB
Fits Get file →
Q5_K_M0.1 GB 0.7 GB
Fits Get file →
Q6_K0.2 GB 0.7 GB
Fits Get file →
Q8_00.2 GB 0.7 GB
Fits Get file →
F160.4 GB 0.9 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_S (0.13 GB) or Q4_K_M (0.14 GB). For 4 GB VRAM, IQ3_S or IQ3_XS (0.11 GB) are suitable. If you have 2 GB VRAM, IQ3_M (0.12 GB) or IQ4_XS (0.12 GB) will fit. Memory estimates are approximate.

What GPU do you need for Biggie SmoLlm 0.15B Base?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is F16 (0.4 GB file, about 1.1 GB in use).

Which Biggie SmoLlm 0.15B Base quant should you choose?

Q4_K_M is the usual starting point for Biggie SmoLlm 0.15B Base: it balances file size and quality well. Here it is a 0.1 GB file.

The Q8_0 file is 0.2 GB, about 1.4 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ3_S at 0.1 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturellama
Parameters181M
Layers35
Trained context2,048 tokens
KV cache (fp16)26 KB per token

Source

Quantized bymradermacher
FamilySmolLM
Licensemit
Downloads (HF)2,769
Last updated2024-08-06

Frequently asked questions about Biggie SmoLlm 0.15B Base

How much VRAM does Biggie SmoLlm 0.15B Base need?

About 0.9 GB at Q4_K_M with an 8K context window. That is the 0.1 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Biggie SmoLlm 0.15B Base on an 8 GB GPU?

Yes, with F16: the 0.4 GB file needs about 1.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Biggie SmoLlm 0.15B Base GGUF?

It depends on the quant: IQ3_S is 0.1 GB, IQ3_XS is 0.1 GB, Q2_K is 0.1 GB, Q3_K_S is 0.1 GB, IQ3_M is 0.1 GB, IQ4_XS is 0.1 GB and 9 more.

What context length does Biggie SmoLlm 0.15B Base support?

The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.1 GB at 2K.

Where can I download Biggie SmoLlm 0.15B Base GGUF?

The files are on Hugging Face in the mradermacher/Biggie-SmoLlm-0.15B-Base-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Biggie SmoLlm 0.15B Base use?

Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run Biggie SmoLlm 0.15B Base on 4 GB VRAM?

Yes, use IQ3_S or IQ3_XS quantizations, each about 0.11 GB in size.

Does this model support vision tasks?

No, the model has no vision capabilities.

What context length does it support?

It supports a 2048 token context window.

Other GGUFs of Biggie-SmoLlm-0.15B-Base

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More SmolLM models

All SmolLM →

Other tiny models

All tiny models →